lumina-ai-inc

chunkr

Document intelligence API in Rust: layout analysis, OCR with bounding boxes, and semantic chunking that turn PDFs, PPTs and Word docs into RAG-ready structured chunks.

4,038 263 Rust AGPL-3.0updated 3 months ago

ocr rag

View on GitHub Dispute this mapping →

Curator's take

The RAG-ingestion specialist: where OCR tools stop at text, Chunkr does layout analysis and SEMANTIC chunking — the chunks arrive respecting document structure, with bounding boxes for citation-grounding. Self-hosted via Docker Compose. Read the split carefully though: the AGPL open-source version runs community models while the paid cloud runs proprietary ones — the README says plainly the accuracy differs; benchmark the OSS tier on YOUR documents before committing. Also ~3 months quiet at review time, and AGPL matters if you embed.

Mapped by ShipWithAI editors · links verified

README.md

Chunkr | Open Source Document Intelligence API

Production-ready service for document layout analysis, OCR, and semantic chunking.
Convert PDFs, PPTs, Word docs & images into RAG/LLM-ready chunks.

Layout Analysis | OCR + Bounding Boxes | Structured HTML & Markdown | Vision-Language Model Processing

👉 Note: The open-source AGPL version is **different** from our fully managed Cloud API. The open-source release uses community/open-source models, while the Cloud API runs **proprietary in-house models** for higher accuracy, speed, and enterprise reliability.

Table of Contents
(Super) Quick Start
Documentation
Open Source vs Cloud API vs Enterprise
Quick Start with Docker Compose
LLM Configuration
Licensing
Connect With Us

Open Source vs Cloud API vs Enterprise

Feature	Open Source Repo (good)	Cloud API - chunkr.ai (best)	Enterprise
Perfect for	Development & testing	Production workloads	Large-scale / High-security
Layout Analysis	Uses open-source models	Proprietary in-house models	In-house + custom-tuned
OCR Accuracy	Community OCR engines	Optimized OCR stack	Optimized + domain-tuned
VLM Processing	Basic open VLMs	Enhanced proprietary VLMs	Custom fine-tunes
Excel Support	❌	✅ Native parser	✅ Native parser
Document Types	PDF, PPT, Word, Images	PDF, PPT, Word, Images, Excel	PDF, PPT, Word, Images, Excel
Infrastructure	Self-hosted	Fully managed cloud	Managed / On-prem
Support	Discord community	Dedicated support	Dedicated founding team
Migration Support	Community-driven	Docs + email	Dedicated migration team

The open-source release is ideal if you want transparency, local hosting, or to experiment with Chunkr’s pipeline.
For best performance, production reliability, and access to in-house models, we recommend the Chunkr Cloud API.
For **high-secu

Continue your stack

What teams reach for next — and why each earns a place beside chunkr. Ranked by curator confidence.

Pairs well with

LlamaIndex

Data framework for connecting custom data sources to LLMs — ingestion, indexing, retrieval.

Why it fitsChunkr slots into LlamaIndex ingestion as the parsing stage — hard documents become structured, citable chunks before indexing.

Chroma

Open-source embedding database for building AI apps with retrieval.

Why it fitsAdjacent RAG pipeline stages: chunkr turns PDFs into RAG-ready semantic chunks; Chroma is the embedding store those chunks land in for retrieval.

Alternative to See all + compare →

MinerU

Heavyweight document-to-markdown/JSON parser — PDFs plus Office (docx/pptx/xlsx) through layout analysis and OCR into LLM-ready output for RAG and agentic pipelines. 73k stars, self-hostable.

Why it fitsSame job — complex documents into LLM-ready data. MinerU is the batteries-included extraction toolkit; Chunkr is an API-shaped service adding semantic chunking and bounding-box citations for RAG pipelines.

olmocr

Open toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.

Why it fitsBoth parse hard documents for AI consumption; olmocr bets on a VLM end-to-end, Chunkr on a layout-analysis pipeline with structured outputs and citations.

chandra

Datalab's SOTA open OCR model: images/PDFs to structured HTML/Markdown/JSON with layout, tables, forms, checkboxes, handwriting and math, in 90+ languages. Local HF or vLLM inference.

Why it fitsOverlapping document-intelligence job at different layers: chunkr is the deployed pipeline API (layout + OCR + chunking); Chandra is the end-to-end OCR model you would slot into such a pipeline.

chunkr

Chunkr | Open Source Document Intelligence API

Table of Contents

Open Source vs Cloud API vs Enterprise

Continue your stack